The Journal of the Convergence on Culture Technology (문화기술의 융합)

The International Promotion Agency of Culture Technology (국제문화기술진흥원)
권호 표지
DOI QR코드

DOI QR Code

Analysis of the Ripple Effect of COVID-19 on Art Auction Using Artificial Neural Network

인공신경망 모형을 활용한 미술품 경매에 대한 COVID-19의 파급효과 분석

  • 이지인 (중앙대학교 문화예술경영학과 ) ;
  • 송정석 (중앙대학교 경제학과 )
  • Received : 2023.01.30
  • Accepted : 2023.03.09
  • Published : 2023.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

This study explores the influence of the COVID-19 pandemic on the Korean art market and contrasts the classic hedonic method of art price prediction with the Artificial Neural Network technique. The empirical analysis of this paper utilizes 14,639 observations of Korean art auction data from 2015 to 2021. There are three types of variables in this study: artist-related, artwork-related, and sales-related. Previous studies have suggested that these three types of variables influence art prices. The empirical findings in this research are in twofold. First, in terms of RMSE and R2, the Artificial Neural Network outperforms the hedonic model. Both techniques discover that sales and artwork variables have a greater impact than artist-related attributes. Second, when the primary factors of art price are controlled, Korean art prices are found to fall dramatically in 2020, shortly following the onset of COVID-19, but to rebound in 2021. The main lesson in this study is that the Artificial Neural Network enhances art price prediction and reduces information asymmetry in the Korean art market even in the face of unanticipated turmoil such as the COVID-19 outbreak.

본 연구에서는 한국 미술품 데이터를 통해 COVID-19의 미술 시장 파급 효과를 분석하고, 전통적인 통계 방법인 헤도닉 모형과 인공신경망의 성능을 R2와 RMSE로 비교 분석하며 미술품 가격을 형성하고 있는 요인의 중요도에 대해 명시적으로 분석해 본다. 헤도닉 모형과 인공신경망의 실증 분석에 사용된 데이터는 2015-2021년의 거래된 한국 미술품 가격 데이터로 총 14,639개를 수집하였다. 각 모형에 적용된 변수는 기존 선행 연구에서 사용되었던 가격형성요인을 참고하여 두 모형 동일하게 적용하였다. 그 결과 COVID-19가 처음 발생하였던 연도인 2020년에는 미술품 가격이 하락하였으나 2021년에는 미술품 가격이 상승한 것으로 나타났다. 헤도닉 모형과 인공신경망의 성능을비교하였을 때 인공신경망의 R2는 0.764, RMSE는 0.076, 헤도닉 모형의 R2는 0.677, RMSE는 1.071로 인공신경망의 성능이 우수한 것으로 나타났다. 또한 중요도를 명시적으로 확인하였을 때 작품적 요인이 크게 작용하였다는 점에 주목할 만하다. 예측하지 못한 상황적 변수로 미술시장이 급변하는 시점에서 본 연구의 결과는 효율적인 미술품 가격 모형을 제시해 줄 것이라 생각한다.

Keywords

References

  1. J. Mei and M. Moses, "Art as an Investment and the underperformance of masterpiece," Ameircan Economic Review, Vol. 92, no. 5, pp. 1656-1668, 2002. https://doi.org/10.2139/ssrn.311701.
  2. J. Kang, H. J. Lee, S. H. Jeong, H. S. Lee and K. J. Oh , "Developing a forecasting model for real estate auction prices using artificial intelligence," Sustainability, Vol. 12, no. 7:2899, 2020. https://doi.org/10.3390/su12072899.
  3. V. Limsombunchai, C. Gan and M. Lee, "House price prediction: Hedonic Price Model vs. Artificial Neural Network," American Journal of Applied Sciences Vol. 1, no. 3, pp. 193-201, 2004. https://doi.org/10.3844/ajassp.2004.193.201.
  4. C. M. Kuan and T. Liu, "Forecasting exchange rates using feedforward and recurrent neural networks," Journal of Applied Econometrics, Vol. 10, no. 4, pp. 347-364, 1995.https://doi.org/10.1002/jae.3950100403.
  5. G. Grudnitski and L. Osburn, "Forecasting S and P and gold futures prices: An application of neural networks," Journal of Futures Markets, Vol. 13, no. 6, pp. 631-643, 1993. https://doi.org/10.1002/fut.3990130605.
  6. D. W. McCann,, "A neural network short-termforecast of significant thunderstorms," Weather and Forecasting, Vol. 7, no. 3, pp. 525-534, 1992. https://doi.org/10.1175/1520-0434(1992)007<0525:annstf>2.0.co;2.
  7. C, Marzban, and G. J. Stumpf, "A neural network for tornado prediction based on doppler radar derives attributes," Journal of Applied Meteorology, Vol. 35, no. 5, pp. 617-626, 1996. htttps://doi.org/10.1175/1520-0450(1996)035<0617:annftp>2.0.co;2.
  8. R. Sharda, "Neural networks for the MS/OR analyst: An application bibliography," Interfaces, Vol. 24, no. 2, pp. 116-130, 1994. https://doi.org/10.1287/inte.24.2.116.
  9. M. W. Gardner, S. R. Dorling, "Artificial neural networks (the multilayer perceptron)-a review of applications in the atmospheric sciences," Atmospheric Environment, Vol. 32, no. 14-15, pp. 2627-2636, 1998. https://doi.org/10.1016/s1352-2310(97)00447-0.
  10. R. Schalkoff, "Pattern Recognition: Statistical, Structural and Neural Approaches," Wiley, 1991.
  11. R. C. Anderson, "Paintings as an investment," Economic Inquiry, Vol. 12, no. 1, pp. 13-26, 1974. https://doi.org/10.1111/j.1465-7295.1974.tb00223.x.
  12. W. J. Baumol, "Unnatural value: or art investment as floating crap game," American Economic Review, Vol. 76, no. 2, pp. 10-14, 1986. https://doi.org/10.1080/07335113.1985.9942162.
  13. J. Pesando, "Art as an investment: the market for modern prints," The American Economic Review, Vol. 83, no. 5, pp. 1075-1089, 1993. https://www.jstor.org/stable/2117549.
  14. M. L. Biey and R. Zanola, "Investment in Paintings: A Short-Run Price Index," Journal of Cultural Economics, Vol. 23, no. 3, pp. 211-222, 1999. https://www.jstor.org/stable/41810697. 10697
  15. W. N. Goetzmann, "Accounting for taste: Art and the financial markets over three centuries," The American Economic Review, Vol. 83, no. 5, pp. 1370-1376, 1993. https://www.jstor.org/stable/2117568.
  16. O. Chanel, L. A. Gerard-Varet and V. Ginsburgh, "Prices and returns on paintings: an exercise on how to price the priceless," The Geneva Papers on Risk and Insurance Theory, Vol. 19, no. 1, pp. 7-21, 1994. https://doi.org/10.1007/bf01112011.
  17. O. Chanel, "Is art market behaviour predictable?," European Economic Review, Vol. 39, no. 3-4, pp. 519-527, 1995. https://doi.org/10.1016/0014-2921(94)00058-8.
  18. O. Chanel, L. A. Gerard-Varet and V. Ginsburgh, "The relevance of Hedonic Price Indices: The case of paintings," Journal of Cultural Economics, Vol. 20, no. 1, pp. 1-24, 1996.https://doi.org/10.1007/s10824-005-1024-3.
  19. H.A.C.K. Hettiarachchi and B.M.S.G. Banneheka, "Time series regression and artificial neural network approaches for forecasting unit price of tea at Colombo auction," Journal of the National Science Foundation of Sri Lanka, Vol. 41, no. 1, pp. 35-40, 2013 https://doi.org/10.4038/jnsfsrv41i1.5331.
  20. I. M. Nasser, M.. Al-Shawwa, S. S. Abu-Naser, "Developing Artificial Neural Network for predicting mobile phone price range," International Journal of Academic Information Systems Research, Vol. 3, no. 2, pp. 1-6, 2019. http://dstore.alazhar.edu.ps/xmlui/handle/123456789/45.
  21. H. Mombeini and A. Yazdani-Chamzini, "Modeling gold price via Artificial Neural Network," Journal of Economics, Business and Management, Vol. 3, no. 7, pp.699-703, 2015. https://doi.org/10.7763/joebm.2015.v3.269.
  22. O. Ashenfelter and K. Graddy, "Auctions and the price of art," Journal of Economics Literature, Vol. 41, no. 3, pp. 763-787, 2003. https://doi.org/10.1257/jel.41.3.763.
  23. K. J. Lancaster, "A new approach to consumer theory," Journal of Political Economy, Vol. 74, no. 2, pp. 132-157, 1966. https://doi.org/10.1086/259131.
  24. Soonim Kim, Youngdae Lee, "A Survey Research on the Auction and Art Price Index," The Journal of the Convergence on Culture Technology(JCCT), Vol. 1, no 2, pp. 37-44, 2015. https://doi.org/10.17703/JCCT.2015.1.2.37.
  25. R. B. Ekelund, Jr, R. W. Ressler and J. K. Watson, "The "Death-Effect" in Art prices: A Demand-side Exploration," Journal of Cultural Economics, Vol. 24, no. 4, pp. 283-300, 2000. http://doi.org/10.1023/A:1007618221648.
  26. Ji In, Lee, Jeong Seok Song, "A Research on Prediction of the Art Price using Multivariate Long Short Term Memory Recurrent Neural Network Deep Learning Model," The Journal of the Korea Contents Association, Vol. 21, no. 6, pp. 552-560, 2021. http://doi.org/10.5392/JKCA.2021.06.552.